Add github workflow to validate samples

.github/workflows/clean-docs.yml

@@ -14,9 +14,9 @@ jobs:
         echo "Slug=$(echo "${{ github.head_ref }}" | sed "s/\//\-/g")" >> "$GITHUB_ENV"
     - name: If no github.head_ref, use last chunk of github.ref as Slug
       if: github.head_ref == ''
-      run: | 
+      run: |
         IFS="\/";
-        read -a strarr <<< "${{ github.ref }}"; 
+        read -a strarr <<< "${{ github.ref }}";
         last_ref="${strarr[${#strarr[*]}-1]}";
         echo "Slug=$(echo $last_ref)" >> "$GITHUB_ENV"
     - name: Document which reference

.github/workflows/docs.yml

@@ -22,9 +22,9 @@ jobs:
         echo "Slug=$(echo "${{ github.head_ref }}" | sed "s/\//\-/g")" >> "$GITHUB_ENV"
     - name: If no github.head_ref, use last chunk of github.ref as Slug
       if: github.head_ref == ''
-      run: | 
+      run: |
         IFS="\/";
-        read -a strarr <<< "${{ github.ref }}"; 
+        read -a strarr <<< "${{ github.ref }}";
         last_ref="${strarr[${#strarr[*]}-1]}";
         echo "Slug=$(echo $last_ref)" >> "$GITHUB_ENV"
     - name: Document which reference

.github/workflows/validate_samples.yml

@@ -0,0 +1,72 @@
+name: Validate-Samples
+
+on:
+  push:
+    paths:
+      - 'samples/*/TIDES/*'
+      - 'spec/*'
+  pull_request:
+    paths:
+      - 'samples/*/TIDES/*'
+      - 'spec/*'
+  workflow_dispatch:
+  create:
+
+jobs:
+  validate:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v2
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.x
+      - name: Install Frictionless
+        run: pip install frictionless[excel,json]>=5.0.0
+      - name: Find Sample Folders
+        id: sample_folders
+        run: |
+          pwd
+          samples=$(find ./samples -type d -name 'TIDES')
+          echo "::set-output name=samples::$samples"
+      - name: Validate Sample Data
+        id: validation
+        run: |
+          samples=(${{ steps.sample_folders.outputs.samples }})
+          results=""
+          for sample in "${samples[@]}"; do
+            result=$(frictionless validate "$sample/datapackage.json" --json)
+            results+="$result\n"
+          done
+          echo "::set-output name=results::$results"
+      - name: Comment on PR
+        if: github.event_name == 'pull_request'
+        uses: actions/github-script@v4
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const samples = '${{ steps.sample_folders.outputs.samples }}'.trim().split('\n');
+            const results = '${{ steps.validation.outputs.results }}'.trim().split('\n');
+            let comment = `**Data Validation Report**\n\n`;
+            comment += '| Sample | Status |\n';
+            comment += '| ------ | ------ |\n';
+            for (let i = 0; i < samples.length; i++) {
+              const sample = samples[i];
+              const result = JSON.parse(results[i]);
+              let status = '';
+              if (result.valid) {
+                status = '![passing](https://via.placeholder.com/20/00ff00/000000?text=+)';
+              } else if (result.stats.errorCount > 0) {
+                status = '![failing](https://via.placeholder.com/20/ff0000/000000?text=+)';
+              } else {
+                status = '![warning](https://via.placeholder.com/20/ffff00/000000?text=+)';
+              }
+              comment += `| ${sample} | ${status} |\n`;
+            }
+            github.issues.createComment({
+                  issue_number: context.issue.number,
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  body: comment
+                });

.pre-commit-config.yaml

@@ -1,24 +1,33 @@
+default_stages: [push]
 repos:
   - repo: https://github.com/psf/black
     rev: 22.8.0
     hooks:
       - id: black
+        stages: [commit]
   - repo: https://github.com/pycqa/flake8
     rev: 5.0.4
     hooks:
     - id: flake8
+      stages: [commit]
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.3.0
     hooks:
       - id: trailing-whitespace
         args: [--markdown-linebreak-ext=md]
+        stages: [commit]
       - id: end-of-file-fixer
+        stages: [commit]
       - id: check-yaml
         args: ["--unsafe"]
+        stages: [commit]
       - id: check-added-large-files
       - id: check-json
+        stages: [commit]
       - id: requirements-txt-fixer
+        stages: [commit]
       - id: mixed-line-ending
+        stages: [commit]
   - repo: https://github.com/igorshubovych/markdownlint-cli
     rev: v0.32.2
     hooks:

CONTRIBUTING.md

@@ -30,49 +30,9 @@ By making any contribution to the projects, contributors self-certify to the [Co
 
 1. [Create a branch](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-and-deleting-branches-within-your-repository) to work on a new issue (or checkout an existing one where the issue is being worked on).  
 2. Make your changes.
-3. Run `pre-commit run --all` to check and fix formatting.
-4. Validate schemas if you have changed them using either [act](https://github.com/nektos/act) or  [frictionless framework](https://framework.frictionlessdata.io/).
-5. [Commit](#commits) your work in `git`
-6. `push` your changes to Github and submit a [`pull request`](#pull-requests)
-
-!!! bug
-
-    Right now some github actions are broken due to some dependencies issues, so please validate changes to schemas using the [frictionless framework](https://framework.frictionlessdata.io/)
-
-??? tip "Manually Validating TIDES Schema Files with Frictionless"
-
-    === "CLI"
-
-        ```sh
-        frictionless validate spec/devices.schema.json
-        frictionless validate spec/fare_transactions.schema.json
-        frictionless validate spec/operators.schema.json
-        frictionless validate spec/passenger_events.schema.json
-        frictionless validate spec/station_activities.schema.json
-        frictionless validate spec/stop_visits.schema.json
-        frictionless validate spec/train_cars.schema.json
-        frictionless validate spec/trips_performed.schema.json
-        frictionless validate spec/vehicle_locations.schema.json
-        frictionless validate spec/vehicle_train_cars.schema.json
-        frictionless validate spec/vehicles.schema.json
-        ```
-
-    === "python"
-
-        ```python
-        import glob
-        from pprint import pprint
-        from frictionless import validate
-
-        schema_paths = glob.glob("spec/**.schema.json")
-        for p in schema_paths:
-            report = validate(p)
-            if not report['valid']:
-                print(f"!!! Invalid:{p}")
-                pprint(report)
-            else: 
-                print(f"Valid:{p}")
-        ```
+3. Run `./test` script to check and fix formatting, validate schemas, and build documentation locally to preview
+4. [Commit](#commits) your work in `git`
+5. `push` your changes to Github and submit a [`pull request`](#pull-requests)
 
 ### Issues
 

mkdocs.yml

@@ -58,7 +58,7 @@ markdown_extensions:
   - pymdownx.tasklist:
       custom_checkbox: true
   - pymdownx.tabbed:
-      alternate_style: true 
+      alternate_style: true
   - pymdownx.superfences:
       custom_fences:
         - name: mermaid

requirements.txt

@@ -1,3 +1,5 @@
 -r docs/requirements.txt
-pre-commit
 frictionless
+jsonschema
+jsonschema-cli
+pre-commit

test

@@ -0,0 +1,24 @@
+#!/usr/bin/env bash
+# Local validation workflows and try to build documentation locally
+echo "1/5 Running precommit"
+pre-commit run --all-files
+
+echo "2/5 Validating table schemas"
+pre-commit run --all-files
+echo "Processing file: $file"
+for file in spec/*schema.json; do
+  echo "Validating: $file"
+  frictionless validate $file
+done
+
+echo "3/5 Validating datapackage"
+json-schema-cli validate https://specs.frictionlessdata.io/schemas/data-package.json spec/datapackage.json
+
+echo "4/5 Validating sample data"
+for file in samples/**/TIDES/datapackage.json; do
+    echo "Validating: $file"
+    frictionless validate --schema-sync $file
+done
+
+echo "5/5 Building documentation"
+mkdocs build